作者: Xiaofeng Liao , Juebang Yu , Guanrong Chen
DOI: 10.1002/CTA.206
关键词:
摘要: In this paper, the bidirectional associative memory (BAM) neural network with axonal signal transmission delay is considered. This model also referred to as a delayed dynamic BAM model. By combining number of different Lyapunov functionals Razumikhin technique, some sufficient conditions for existence unique equilibrium and global asymptotic stability are derived. These results fairly general can be easily verified. Besides, approach analysis allows one consider several types activation functions, including piecewise linear sigmoids bounded activations well C1-smooth sigmoids. It believed that these significant convenient in design applications networks. Copyright © 2002 John Wiley & Sons, Ltd.